Jump to Content
Lesly Miculicich

Lesly Miculicich

I'm a Senior Research Engineer at Google in the Cloud AI Research team. Previously, I was Researcher at Microsoft where I focussed on text summarization and generation. I received my PhD degree from EPFL in Switzerland, and serve as research assistant at the Idiap Research Institute where I worked on machine translation. My current interest is on text generation, general natural language processing, and machine learning.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, desc
  • Year
  • Year, desc
    Preview abstract Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verification. Compared with generic reasoning, table-based reasoning requires the extraction of underlying semantics from both free-form questions and semi-structured tabular data. Chain-of-Thought and its similar approaches incorporate the reasoning chain in the form of textual context, but it is still an open question how to effectively leverage tabular data in the reasoning chain. We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts. Specifically, we guide LLMs using in-context learning to iteratively generate operations and update the table to represent a tabular reasoning chain. LLMs can therefore dynamically plan the next operation based on the results of the previous ones. This continuous evolution of the table forms a chain, showing the reasoning process for a given tabular problem. The chain carries structured information of the intermediate results, enabling more accurate and reliable predictions. Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks across multiple LLM choices. View details
    Transformers as Graph-to-Graph Models
    James Henderson
    Alireza Mohammadshahi
    Andrei C. Coman
    Association for Computational Linguistics, (2023), pp. 93-107
    Preview abstract We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability explicit, by inputting graph edges into the attention weight computations and predicting graph edges with attention-like functions, thereby integrating explicit graphs into the latent graphs learned by pretrained Transformers. Adding iterative graph refinement provides a joint embedding of input, output, and latent graphs, allowing non-autoregressive graph prediction to optimise the complete graph without any bespoke pipeline or decoding strategy. Empirical results show that this architecture achieves state-of-the-art accuracies for modelling a variety of linguistic structures, integrating very effectively with the latent linguistic representations learned by pretraining. View details
    No Results Found